Natural Language Generation Using Reinforcement Learning with External Rewards.
Vidhushini SrinivasanSashank SanthanamSamira ShaikhPublished in: CoRR (2019)
Keyphrases
- natural language generation
- reinforcement learning
- markov decision processes
- natural language processing
- function approximation
- dialogue system
- state space
- dialog systems
- word order
- machine translation
- natural language
- model free
- dialogue management
- text generation
- reinforcement learning algorithms
- aggregated search
- multi agent
- temporal difference
- learning algorithm
- optimal policy
- general purpose
- dynamic programming
- reward function
- action selection
- artificial intelligence
- machine learning
- knowledge base
- markov decision problems
- control policy
- markov decision process
- computational intelligence